plotCluster: Plot a summary of a given cluster from Step 2 of SCALPEL.

Description

We plot the preliminary dictionary elements that correspond to a given dictionary element, derived during Step 2 of SCALPEL, or a given component included in the sparse group lasso of Step 3.

Usage

plotCluster(
  scalpelOutput,
  AIndex = NULL,
  AfilterIndex = NULL,
  pctTransp = 0.01
)

Arguments

scalpelOutput

An object returned by one of the SCALPEL functions: scalpel, scalpelStep2, or scalpelStep3.

AIndex

The dictionary element (i.e., cluster) of interest. The index refers to the column of scalpelOutput$A, which is part of the output from scalpelStep2. Specify AIndex or AfilterIndex, not both.

AfilterIndex

The refined dictionary element of interest. The index refers to the column of scalpelOutput$Afilter, which is part of the output from scalpelStep3. Note that the class of scalpelOutput must be scalpel or scalpelStep3 if specifying AfilterIndex. Specify AIndex or AfilterIndex, not both.

pctTransp

The percent transparency (in [0,1]) for the colors used to plot the preliminary dictionary elements. The default value is 0.01.

Value

None

Details

The left plot shows the dictionary element of interest in orange, with the other dictionary elements shown in blue. The middle plot shows all of the preliminary dictionary elements corresponding to the dictionary element plotted transparently. The right plot shows the dictionary element in orange, along with the union of all of the preliminary dictionary elements in gray. Note that the plots in the middle and on the right are zoomed-in, compared to the plot on the left that shows the entire field of view for the video.

Examples

Run this code

# NOT RUN {
### many of the functions in this package are interconnected so the
### easiest way to learn to use the package is by working through the vignette,
### which is available at ajpete.com/software

#assumes you have run the example for the "scalpel" function
#plots the cluster for the 2nd dictionary element (i.e., scalpelOutput$A[,2])
plotCluster(scalpelOutput = scalpelOutput, AIndex = 2)
#plots the cluster for the 2nd component included in SGL (i.e., scalpelOutput$Afilter[,2])
plotCluster(scalpelOutput = scalpelOutput, AfilterIndex = 2)
# }